Borrowing it
Nothing to install: this file belongs to sdsrss/claude-mem-lite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sdsrss/claude-mem-lite/main/CLAUDE.mdgit clone --depth 1 https://github.com/sdsrss/claude-mem-liteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sdsrss/claude-mem-lite/claude-md)<a href="https://agentmods.dev/instructions/sdsrss/claude-mem-lite/claude-md"><img src="https://agentmods.dev/badge/instructions/sdsrss/claude-mem-lite/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/sdsrss/claude-mem-lite/claude-md"><img src="https://agentmods.dev/badge/instructions/sdsrss/claude-mem-lite/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05307 | $0.05307 |
| Opus 5.5 | $0.02123 | $0.02123 |
| Sonnet 5.5 | $0.01061 | $0.01061 |
| Haiku 4.5 | $0.00531 | $0.00531 |
Grade A, and why
claude-mem-lite CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Lightweight persistent memory for Claude Code. MCP server + hooks plugin.
- Version: 6.30.5 — this exact string is a release guard.
tests/install-e2e.test.mjsasserts CLAUDE.md contains**Version**: <v>matchingpackage.json,plugin.jsonandmarketplace.json. Do not reformat this line. - Runtime: Node >=22 (20 dropped in v4.0.0), ESM · npm · better-sqlite3 + FTS5
Capped at 20 KB: RULES ONLY. Each rule was expensive to establish and several shipped as
a WRONG draft first, so these one-liners are TRIGGERS, not the argument. The evidence is
verbatim in the tracked appendix a fresh clone gets — docs/measurement/findings.md
(invariants, doctrine, calibers), baselines.md, rulers.md, docs/audit*/. Read it
before retrieval, measurement, release, migration or schema work.
Commands
| Task | Command |
|---|---|
| Setup · tests | npm install · npx vitest run · one file npx vitest run tests/foo.test.mjs · one case -t 'case name' · before tagging npm run test:ci-env (CI env) |
| Coverage | npm run test:coverage (gate: statements 81 / branches 75 / functions 87 / lines 83) |
| Lint · shell | npx eslint . · shellcheck scripts/*.sh |
| Format | npm run format — run it twice, tests/hook-update.test.mjs needs a second pass to reach a fixed point. format:check is gated in CI and pre-commit |
| Dead code | npm run dead-code (knip — measure from the primary working tree; the NAME SET is the evidence, not the count) |
| Plugin manifests | npm run validate:manifests — claude plugin validate . --strict is NOT equivalent: it never checks .claude-plugin/plugin.json |
| Bench · multipliers | npm run benchmark:gate · benchmark:multipliers:gate — run the second after touching any constant in scoring-sql.mjs or MULT_EXPR; the first is structurally blind to those |
| Recapture the gate baseline | node benchmark/benchmark.mjs --production-hybrid > benchmark/baseline.json — expires 30 days after its own timestamp, and CI + publish pass --strict. Sampled 2026-10-07T16:18:48Z → red from 2026-11-06 16:18 UTC. The stamp lives in THREE places (baseline.json, ci.yml, this row); tests/baseline-stamp-sync.test.mjs fails if they disagree. Recapture BEFORE tagging, in its own commit — otherwise it goes red after the tag is pushed |
| Audit metrics | npm run audit:metrics · audit:baseline · audit:selfcheck |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed e9ec65ad66b6
- yesterday Changed dd4560d15459
- 2d ago Changed cdd52a94581f
- 3d ago Changed 122dc593daa4
- 4d ago Changed eb17002142f9
- 6d ago Changed 929b930c6063
- 7d ago Changed · -22 tokens per session be80ff1b0570
- 8d ago Changed · +32 tokens per session 04c5361cf0ec
- 15d ago Changed 8185be8fa7ca
- 16d ago First seen · 215 lines · 5,297 tokens per session scan A 801f996caa12
claude-mem-lite CLAUDE.md is an instructions file published in the GitHub repository sdsrss/claude-mem-lite (67 stars, last pushed today), licensed MIT. It adds 5,307 tokens to every session, about $0.0212 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).